Simplify
Use when a file or module has grown too complex — removes unnecessary abstractions, dead code, and over-engineering without changing behavior. Invoke after implementing a feature when the code feels over-engineered.From its SKILL.md
npx -y skills add latuconsinafr/claude-code-config --skill simplifyAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.7 KB, 308 tokens by cl100k_base, as published. Nobody here has run it
Simplify
Simplify the code in $ARGUMENTS (file or module path).
If no argument — simplify the most recently edited file.
Guiding principle
The best code is code that doesn't exist. The second best is code that's obvious.
Spawn the refactoring agent
The refactoring agent handles the full simplification workflow: test baseline verification, blast radius checks, identifying complexity sources, proposing and applying changes one at a time, and re-running tests after each step.
Spawn it with the following task:
Target: <file or module path from $ARGUMENTS, or most recently edited file>
Goal: simplify — remove unnecessary abstractions, dead code, and over-engineering
without changing behavior
Constraint: behavior must be identical before and after each change
The agent will:
- Verify the test suite is green before starting
- Warn if on
main/masterbranch - Check blast radius for every symbol it considers removing
- Propose changes grouped by risk (safe / needs verification / out of scope)
- Ask for confirmation before applying
- Apply and re-run tests after each change, reverting on failure
After the agent completes
Review the agent's summary:
- All changes made and tests verified
- Any blocked changes (failed tests on attempt) — note these for a separate follow-up
- Deferred items (bugs or features noticed but not touched during refactor)
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 1 of the 12 instructions most refactoring skills give in 308 tokens
Counted across 521 of the 525 authors here whose files we hold, read 2026-08-07
- Run tests after each changehere, and in 52 of 521
- Run the full test suite after each stepin 32 of 521
- Preserve external behaviorin 27 of 521, across 24 files
- Remove dead codein 26 of 521
- Write tests before refactoringin 26 of 521, across 25 files
- Make small incremental changesin 19 of 521, across 16 files
- Break the implementation into tiny commitsin 18 of 521, across 5 files
- Ask the user about alternative optionsin 17 of 521, across 4 files
- Create a GitHub issue with the planin 17 of 521, across 4 files
- Explore the repository to verify assertionsin 17 of 521, across 4 files
- Interview the user about the refactorin 16 of 521, across 3 files
- Check the codebase for test coveragein 16 of 521, across 3 files
Said here and by no other author read
- simplify the specified file or module
- simplify the most recently edited file if no argument is given
- spawn the refactoring agent
- warn if on the main or master branch
- check blast radius for every symbol considered for removal
- propose changes grouped by risk
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.